daiso-cli
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the daiso CLI tool via npx to perform search and retrieval tasks. This involves running shell commands with user-supplied arguments such as keywords, locations, and theater codes.
- [EXTERNAL_DOWNLOADS]: The skill uses npx to download and run the daiso package from the public npm registry. It also references a remote Model Context Protocol (MCP) endpoint at https://mcp.aka.page and a project homepage on GitHub.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external retail and cinema APIs which could theoretically contain instructions intended to influence the agent. (1) Ingestion points: Output from the daiso CLI commands for products, inventory, and cinemas in SKILL.md. (2) Boundary markers: No explicit markers or instructions to ignore embedded instructions are provided. (3) Capability inventory: The skill has command execution capabilities through npx. (4) Sanitization: No input or output sanitization is specified in the skill instructions.
Audit Metadata